FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding

arXiv:2311.15965v2 Announce Type: replace
Abstract: Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and background shift challenges in continual learning. However, fairness, another major challenge that causes unfair predictions leading to low performance among major and minor classes, still needs to be well addressed. In addition, prior methods have yet to model the unknown classes well, thus resulting in …

abstract arxiv attention catastrophic forgetting challenge challenges continual cs.cv dynamic environments fairness falcon however knowledge learn major modeling prior segmentation semantic shift studies type understanding via while